arXiv:2509.25361v1 Announce Type: new Abstract: Reward Models (RMs) are key components for evaluating and guiding language model outputs. However, traditional scalar RMs often struggle with incorporating contextual and background information during inference, leading to incomplete evaluations. Generative RMs (GRMs) attempt…
arXiv:2509.12838v2 Announce Type: replace-cross Abstract: It is crucial to efficiently execute instructions such as “Find an apple and a banana” or “Get ready for a field trip,” which require searching for multiple objects or understanding context-dependent commands. This study addresses…
arXiv:2509.25370v1 Announce Type: new Abstract: Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading failures, where a single root-cause error…
arXiv:2509.25977v1 Announce Type: cross Abstract: Federated learning (FL) is a distributed learning paradigm across multiple entities while preserving data privacy. However, with the continuous emergence of new data and increasing model diversity, traditional federated learning faces significant challenges, including inherent…
arXiv:2509.25373v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) strive to achieve a profound, human-like understanding of and interaction with the physical world, but often exhibit a shallow and incoherent integration when acquiring information (Perception) and conducting reasoning (Cognition).…
arXiv:2509.26139v1 Announce Type: cross Abstract: There is high demand on fire simulations, in both scale and quantity. We present a multi-pronged approach to improving the time and energy required to meet these demands. We show the ability of a custom…
arXiv:2509.25374v1 Announce Type: new Abstract: Longitudinal medical visual question answering (Diff-VQA) requires comparing paired studies from different time points and answering questions about clinically meaningful changes. In this setting, the difference signal and the consistency of visual focus across time…
arXiv:2509.26281v1 Announce Type: cross Abstract: Driven by the growing need for Oriented Object Detection (OOD), learning from point annotations under a weakly-supervised framework has emerged as a promising alternative to costly and laborious manual labeling. In this paper, we discuss…
arXiv:2509.25411v1 Announce Type: new Abstract: We propose ImitSAT, a branching policy for conflict-driven clause learning (CDCL) solvers based on imitation learning for the Boolean satisfiability problem (SAT). Unlike previous methods that predict instance-level signals to improve CDCL branching indirectly, or…
arXiv:2509.26433v1 Announce Type: cross Abstract: When used in high-stakes settings, AI systems are expected to produce decisions that are transparent, interpretable, and auditable, a requirement increasingly expected by regulations. Decision trees such as CART provide clear and verifiable rules, but…
